[R] Correlation Loops in time series

arun smartpink111 at yahoo.com
Wed Jul 31 17:15:43 CEST 2013



Hi,
May be this helps:

set.seed(25)
mt1<- matrix(sample(c(NA,1:40),20*200,replace=TRUE),ncol=200)

set.seed(487)
mt2<- matrix(sample(c(NA,1:80),20*200,replace=TRUE),ncol=200)
res<- sapply(seq_len(ncol(mt1)),function(i) cor(mt1[,i],mt2[,i],use="complete.obs",method="pearson"))


A.K.




Hello, I've got the following problem. 
I have to matrices each containing 200 time series. 
Now I want to calculate the correlation of the first time series of each of the matrices. 
I use the following command: 
cor(mts1[,1],mts2[,1], use="complete.obs", method=c("pearson")) 
cor(mts1[,2],mts2[,2], use="complete.obs", method=c("pearson")) 
cor(mts1[,3],mts2[,3], use="complete.obs", method=c("pearson")) 
and so on.. 
I would like to repeat this for each of the 200 time series. As it 
is quite painful to change the command 200 times I wanted to ask if 
there's a loop function that can cover these series in a fast way? 
Thanks in advance for your help 
Best 
Tom



More information about the R-help mailing list